The initial noise present in the depth images obtained with RGB-D sensors is a combination of hardware limitations in addition to the environmental factors,due to the limited capabilities of sensors,which also produce...The initial noise present in the depth images obtained with RGB-D sensors is a combination of hardware limitations in addition to the environmental factors,due to the limited capabilities of sensors,which also produce poor computer vision results.The common image denoising techniques tend to remove significant image details and also remove noise,provided they are based on space and frequency filtering.The updated framework presented in this paper is a novel denoising model that makes use of Boruta-driven feature selection using a Long Short-Term Memory Autoencoder(LSTMAE).The Boruta algorithm identifies the most useful depth features that are used to maximize the spatial structure integrity and reduce redundancy.An LSTMAE is then used to process these selected features and model depth pixel sequences to generate robust,noise-resistant representations.The system uses the encoder to encode the input data into a latent space that has been compressed before it is decoded to retrieve the clean image.Experiments on a benchmark data set show that the suggested technique attains a PSNR of 45 dB and an SSIM of 0.90,which is 10 dB higher than the performance of conventional convolutional autoencoders and 15 times higher than that of the wavelet-based models.Moreover,the feature selection step will decrease the input dimensionality by 40%,resulting in a 37.5%reduction in training time and a real-time inference rate of 200 FPS.Boruta-LSTMAE framework,therefore,offers a highly efficient and scalable system for depth image denoising,with a high potential to be applied to close-range 3D systems,such as robotic manipulation and gesture-based interfaces.展开更多
This study aims to develop an accurate and robust machine learning model to predict the carbonation depth of fly ash concrete,overcoming the limitations of traditional predictive methods.Five ensemble-based models,suc...This study aims to develop an accurate and robust machine learning model to predict the carbonation depth of fly ash concrete,overcoming the limitations of traditional predictive methods.Five ensemble-based models,such as adaptive boosting(AdaBoost),categorical boosting(CatBoost),gradient boosting regressor(GBR),hist gradient boosting regressor(HistGBR),and extreme gradient boosting(XGBoost),were developed and optimized using 729 high-quality dataset points incorporating seven input parameters,including cement,CO_(2),exposure time,water-binder ratio,fly ash,curing time,and compressive strength.Several performance evaluation metrics were used to compare the models.The GBR model emerged as the best-performing model,based on high coefficient of determination(R^(2))values and balanced error metrics across both validation and testing datasets.While all models performed exceptionally well on the training data,GBR demonstrated superior generalization capability,with R^(2) values of 0.9438 on the validation set and 0.9310 on the testing set.Furthermore,its low mean squared error(MSE),root mean square error(RMSE),mean absolute error(MAE),and median absolute error(MdAE)confirmed its robustness and accuracy.Moreover,shapley additive explanations(SHAP)analysis enhanced the interpretability of predictions,highlighting the curing time and exposure time as the most critical drivers of carbonation depth.展开更多
Objective:To explore the relationship between anesthetic depth and surgical stress response in minimally invasive cardiothoracic surgery.Methods:A total of 89 patients who underwent thoracoscopic minimally invasive ca...Objective:To explore the relationship between anesthetic depth and surgical stress response in minimally invasive cardiothoracic surgery.Methods:A total of 89 patients who underwent thoracoscopic minimally invasive cardiothoracic surgery in our hospital from June 2024 to December 2024 were selected as the research objects.They were divided into the light anesthesia group(n=45)and the deep anesthesia group(n=44).The vital signs at different intraoperative nodes and perioperative stress status of the two groups were compared.Results:Before lesion resection and after surgery,the mean arterial pressure and heart rate of the deep anesthesia group were lower than those of the light anesthesia group,with statistically significant differences.Conclusion:In thoracoscopic minimally invasive cardiothoracic surgery,deep anesthesia can effectively control the patient’s surgical stress response,but the postoperative awakening time is longer;patients under light anesthesia have a shorter awakening time,but the intraoperative stress response is obvious.展开更多
Presented in this study is a novel method for estimating the depth of single underwater source in shallow water,utilizing vector sensors.The approach leverages the depth distribution of the broadband Stokes parameters...Presented in this study is a novel method for estimating the depth of single underwater source in shallow water,utilizing vector sensors.The approach leverages the depth distribution of the broadband Stokes parameters to estimate source depth accurately.Unlike traditional matched field processing(MFP)and matched mode processing(MMP),the proposed approach can estimate source depth directly from the data received by sensors without requiring complete environmental information.Firstly,the broadband Stokes parameters(BSP)are established using the normal mode theory.Then the nonstationary phase approximation is used to simplify the theoretical derivation,which is necessary when dealing with broadband integrals.Additionally,range terms of the BSP are eliminated by normalization.By analyzing the depth distribution of the normalized broadband Stokes parameters(NBSP),it is found that the NBSP exhibit extreme values at the source depth,which can be used for source depth estimation.So the proposed depth estimation method is based on searching the peaks of the NBSP.Simulations show that this method is effective in relatively simple shallow water environments.Finally,the effect of source range,frequency bandwidth,sound speed profile(SSP),water depth,and signal-to-noise ratio(SNR)are studied.The findings indicate that the proposed method can accurately estimate the source depth when the SNR is greater than-5 d B and does not need to consider model mismatch issues.Additionally,variations in environmental parameters have minimal impact on estimation accuracy.Compared to MFP,the proposed method requires a higher SNR,but demonstrates superior robustness against fluctuations in environmental parameters.展开更多
Accurately estimating depth from underwater monocular images is essential for the target tracking task of unmanned underwater vehicles.This work proposes a method based on the Lpg-Lap Unet architecture.First,the Unet ...Accurately estimating depth from underwater monocular images is essential for the target tracking task of unmanned underwater vehicles.This work proposes a method based on the Lpg-Lap Unet architecture.First,the Unet architecture integrates Laplacian pyramid depth residuals and Sobel operators to improve the boundary details in depth images,which may suffer from the feature loss caused by upsampling and the blurriness of underwater images.Multiscale local planar guidance layers then fully exploit the intermediate depth features,and a comprehensive loss function ensures robustness and accuracy.Experimental results on benchmarks demonstrate the effectiveness of Lpg-Lap Unet and its superior performance over state-of-the-art models.An underwater target tracking system is then designed to further validate its real-time capabilities in the AirSim simulation platform.展开更多
Bathymetric measurement of shallow water is of fundamental importance to coastal environment research and resource management.However,there are still great challenges in estimating water depth using satellite observat...Bathymetric measurement of shallow water is of fundamental importance to coastal environment research and resource management.However,there are still great challenges in estimating water depth using satellite observations in turbid coastal waters.In this paper,we developed a physicsenhanced deep neural network to estimate bathymetry of highly turbid waters of the Changjiang(Yangtze)River estuary from dual-polarized synthetic aperture radar(SAR)images.Sentinel-1A/B SAR images with a spatial resolution of 20 m×22 m were collected and matched with water depth data from nautical charts during 2017-2023.For the input parameters of the model,in addition to the normalized radar backscatter cross section(NRCS)at single polarization and incidence angle,the impacts of both polarimetric characteristics and physical environmental factors on model performance were discussed in detail.Results of feature importance analysis and sensitivity experiments indicate that the polarization ratio and NRCS after removing the influence of background sea surface wind field make significant contributions to the bathymetry retrieval model.The root mean square error(RMSE)of SAR derived water depth decreases from 1.44 to 0.78 m within 0-30-m depth,and the mean relative error(MRE)is reduced from 15.6%to 8.6%.Compared with other machine learning models such as ResNet,XGBoost,and Random Forest,the MRE is reduced by 3.9%,5.7%,and 7.4%,respectively.The spatial distribution of SAR derived water depth also exhibits a high degree of consistency with observations,demonstrating the great potential of the model in estimating the depth of turbid shallow waters.展开更多
Depth maps play a crucial role in various practical applications such as computer vision,augmented reality,and autonomous driving.How to obtain clear and accurate depth information in video depth estimation is a signi...Depth maps play a crucial role in various practical applications such as computer vision,augmented reality,and autonomous driving.How to obtain clear and accurate depth information in video depth estimation is a significant challenge faced in the field of computer vision.However,existing monocular video depth estimation models tend to produce blurred or inaccurate depth information in regions with object edges and low texture.To address this issue,we propose a monocular depth estimation model architecture guided by semantic segmentation masks,which introduces semantic information into the model to correct the ambiguous depth regions.We have evaluated the proposed method,and experimental results show that our method improves the accuracy of edge depth,demonstrating the effectiveness of our approach.展开更多
Self-supervised monocular depth estimation has emerged as a major research focus in recent years,primarily due to the elimination of ground-truth depth dependence.However,the prevailing architectures in this domain su...Self-supervised monocular depth estimation has emerged as a major research focus in recent years,primarily due to the elimination of ground-truth depth dependence.However,the prevailing architectures in this domain suffer from inherent limitations:existing pose network branches infer camera ego-motion exclusively under static-scene and Lambertian-surface assumptions.These assumptions are often violated in real-world scenarios due to dynamic objects,non-Lambertian reflectance,and unstructured background elements,leading to pervasive artifacts such as depth discontinuities(“holes”),structural collapse,and ambiguous reconstruction.To address these challenges,we propose a novel framework that integrates scene dynamic pose estimation into the conventional self-supervised depth network,enhancing its ability to model complex scene dynamics.Our contributions are threefold:(1)a pixel-wise dynamic pose estimation module that jointly resolves the pose transformations of moving objects and localized scene perturbations;(2)a physically-informed loss function that couples dynamic pose and depth predictions,designed to mitigate depth errors arising from high-speed distant objects and geometrically inconsistent motion profiles;(3)an efficient SE(3)transformation parameterization that streamlines network complexity and temporal pre-processing.Extensive experiments on the KITTI and NYU-V2 benchmarks show that our framework achieves state-of-the-art performance in both quantitative metrics and qualitative visual fidelity,significantly improving the robustness and generalization of monocular depth estimation under dynamic conditions.展开更多
Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical models.Machine learning can effectively solve this issue and has been proven useful in th...Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical models.Machine learning can effectively solve this issue and has been proven useful in the prediction of groundwater depth in many areas.In this study,two new models are applied to the prediction of groundwater depth in the Ningxia area,China.The two models combine the improved dung beetle optimizer(DBO)algorithm with two deep learning models:The Multi-head Attention-Convolution Neural Network-Long Short Term Memory networks(MH-CNN-LSTM)and the Multi-head Attention-Convolution Neural Network-Gated Recurrent Unit(MH-CNN-GRU).The models with DBO show better prediction performance,with larger R(correlation coefficient),RPD(residual prediction deviation),and lower RMSE(root-mean-square error).Com-pared with the models with the original DBO,the R and RPD of models with the improved DBO increase by over 1.5%,and the RMSE decreases by over 1.8%,indicating better prediction results.In addition,compared with the multiple linear regression model,a traditional statistical model,deep learning models have better prediction performance.展开更多
Rare earth-doped inorganic compounds contribute mostly to the family of persistent luminescent materials due to the versatile energy levels of rare earth ions.One of the key research aims is to match the trap level st...Rare earth-doped inorganic compounds contribute mostly to the family of persistent luminescent materials due to the versatile energy levels of rare earth ions.One of the key research aims is to match the trap level stemming from the doped rare earth ion or intrinsic defects to the electronic structure of the host,and therefore thermoluminescence measurement becomes a radical technology in studying trap depth,which is one of the significant parameters that determine the properties of persistent luminescence and photostimulated luminescence.However,the results of trap depth obtained by different thermoluminescence methods are quite different so that they are not comparable.Herein,we analyzed different thermoluminescence methods,selected and improved the traditional peak position method of T_(m)/500 to be E=(-0.94Inβ+30.09)kT_(m).Only the experimental heating rate(β)is needed additionally,but the accuracy is improved greatly in most cases.This convenient and accurate method will accelerate the discovery of novel rare earth-doped materials.展开更多
Spatial computing and augmented reality are advancing rapidly,with the goal of seamlessly blending virtual and physical worlds.However,traditional depth-sensing systems are bulky and energy-intensive,limiting their us...Spatial computing and augmented reality are advancing rapidly,with the goal of seamlessly blending virtual and physical worlds.However,traditional depth-sensing systems are bulky and energy-intensive,limiting their use in wearable devices.To overcome this,recent research by X.Liu et al.presents a compact binocular metalens-based depth perception system that integrates efficient edge detection through an advanced neural network.This system enables accurate,realtime depth mapping even in complex environments,enhancing potential applications in augmented reality,robotics,and autonomous systems.展开更多
The tilt-depth method can be used to make fast estimation of the top depth of magnetic bodies. However, it is unable to estimate bottom depths and its every inversion point only has a single solution. In order to reso...The tilt-depth method can be used to make fast estimation of the top depth of magnetic bodies. However, it is unable to estimate bottom depths and its every inversion point only has a single solution. In order to resolve such weaknesses, this paper presents an improved tilt-depth method based on the magnetic anomaly expression of vertical contact with a finite depth extent, which can simultaneously estimate top and bottom depths of magnetic bodies. In addition, multiple characteristic points are selected on the tilt angle map for joint computation to improve reliability of inversion solutions. Two- and three- dimensional model tests show that this improved tilt-depth method is effective in inverting buried depths of top and bottom bodies, and has a higher inversion precision for top depths than the conventional method. The improved method is then used to process aeromagnetic data over the Changling Fault Depression in the Songliao Basin, and inversion results of top depths are found to be more accurate for actual top depths of volcanic rocks in two nearby drilled wells than those using the conventional tilt-depth method.展开更多
During upward horizontal stratified backfill mining,stable backfill is essential for cap and sill pillar recovery.Currently,the primary method for calculating the required strength of backfill is the generalized three...During upward horizontal stratified backfill mining,stable backfill is essential for cap and sill pillar recovery.Currently,the primary method for calculating the required strength of backfill is the generalized three-dimensional(3 D)vertical stress model,which ignores the effect of mine depth,failing to obtain the vertical stress at different positions along stope length.Therefore,this paper develops and validates an improved 3 D model solution through numerical simulation in Rhino-FLAC^(3D),and examines the stress state and stability of backfill under different conditions.The results show that the improved model can accurately calculate the vertical stress at different mine depths and positions along stope length.The error rates between the results of the improved model and numerical simulation are below 4%,indicating high reliability and applicability.The maximum vertical stress(σ_(zz,max))in backfill is positively correlated with the degree of rock-backfill closure,which is enhanced by mine depth and elastic modulus of backfill,while weakened by stope width and inclination,backfill friction angle,and elastic modulus of rock mass.Theσ_(zz,max)reaches its peak when the stope length is 150 m,whileσ_(zz,max)is insensitive to changes in rock-backfill interface parameters.In all cases,the backfill stability can be improved by reducingσ_(zz,max).The results provide theoretical guidance for the backfill strength design and the safe and efficient recovery of ore pillars in deep mining.展开更多
Coal seam water injection in tunnels is an effective technical measure for preventing coal mine rock bursts.This study used the improved split Hopkinson pressure bar(SHPB)to apply three equal static stresses to water-...Coal seam water injection in tunnels is an effective technical measure for preventing coal mine rock bursts.This study used the improved split Hopkinson pressure bar(SHPB)to apply three equal static stresses to water-saturated coal to simulate the initial stress environment of coal at different depths.Then,dynamic mechanical experiments were conducted on the saturated coal at different depths to investigate the effects of water saturation and depth on the coal samples’dynamic mechanical properties.Under uniaxial compression and without lateral compression,the strength of coal samples decreased to varying degrees in the saturated state;under different depth conditions,the dynamic strength of coal in the saturated state decreased compared with that in the natural state.However,compared with that at 0 m,the reduction in the strength of coal under the saturated condition at 200,400,600,and 800 m was significantly reduced.The findings of this study provide a basic theoretical foundation for the prevention and control of dynamic coal mine disasters.展开更多
Eye depth is an important agronomic trait affecting tubers'appearance,quality,and processing suitability.Hence,cultivating varieties with uniform shapes and shallow eye depth are important goals for potato breedin...Eye depth is an important agronomic trait affecting tubers'appearance,quality,and processing suitability.Hence,cultivating varieties with uniform shapes and shallow eye depth are important goals for potato breeding.In this study,based on the primary mapping of the tuber eyedepth locus using a small primary-segregating population,a large secondary-segregating population with 2100 individuals was used to map the eye-depth locus further.A major quantitative trait locus for eye-depth on chromosome 10 was identified(designated qEyd10.1)using BSAseq and traditional QTL mapping methods.The qEyd10.1 could explain 55.0%of the eye depth phenotypic variation and was further narrowed to a 309.10 kb interval using recombinant analysis.To predict candidate genes,tissue sectioning and RNA-seq of the specific tuber tissues were performed.Genes encoding members of the peroxidase superfamily with likely roles in indole acetic acid regulation were considered the most promising candidates.These results will facilitate marker-assisted selection for the shallow-eye trait in potato breeding and provide a solid basis for eye-depth gene cloning and the analysis of tuber eye-depth regulatory mechanisms.展开更多
AIM:To assess visual outcomes and satisfaction of a non-diffractive extended depth of focus(EDOF)intraocular lens(IOL)in individuals with ocular hypertension(OHT)and well-controlled mild glaucoma undergoing cataract s...AIM:To assess visual outcomes and satisfaction of a non-diffractive extended depth of focus(EDOF)intraocular lens(IOL)in individuals with ocular hypertension(OHT)and well-controlled mild glaucoma undergoing cataract surgery.METHODS:An investigator-initiated,single-center,prospective,interventional,noncomparative study conducted in Montreal,Canada.The study enrolled 31 patients(55 eyes)with OHT or mild glaucoma who received a non-diffractive EDOF IOL(Acrysof IQ Vivity).Participants underwent sequential cataract surgery with the Vivity IOL.Follow-up evaluations occurred at 1d,1,and 3mo postoperatively,assessing uncorrected distance,intermediate,and near visual acuity.Questionnaires(QUVID:Questionnaire for visual disturbances and IOLSAT:Intraocular lens satisfaction)were administered pre and post-operatively to measure visual disturbances and spectacle independence in various lighting.Safety parameters included intraocular pressure(IOP),glaucoma medications,spherical equivalence,mean deviation and pattern standard deviation or square root of lost variance on Octopus visual field.RESULTS:At 1 and 3mo postoperatively,significant improvements were observed in uncorrected distance and intermediate visual acuity.Spectacle independence was enhanced for distance and intermediate vision,especially in bright light settings.Spectacle-free intermediate vision was improved even in dim lighting.Visual disturbances,particularly glare symptoms,were reduced,and there was a notable decrease in IOP and glaucoma medication burden at 3mo.There was more hazy vision postoperatively with no impact on visual acuity and visual satisfaction.CONCLUSION:The non-diffractive EDOF lens improves distance and intermediate spectacle-free visual function in patients with OHT and well-controlled glaucoma.The findings highlight significant improvements in visual acuity,reduced glare,enhanced spectacle independence,and improved visual performance in different lighting conditions.展开更多
Maintaining the s-polarization state of laser beams is important to achieve high modulation depth in a laser-interference-based super-resolution structured illumination microscope(SR-SIM).However,the imperfect optical...Maintaining the s-polarization state of laser beams is important to achieve high modulation depth in a laser-interference-based super-resolution structured illumination microscope(SR-SIM).However,the imperfect optical components can depolarize the laser beams hence degenerating the modulation depth.Here,we first presented a direct measurement method designed to estimate the modulation depth more precisely by shifting illumination patterns with equal phase steps.This measurement method greatly reduces the dependence of modulation depths on the samples,and then developed a polarization optimization method to achieve high modulation depth at all orientations by actively and quantitatively compensating for the additional phase difference using a combination of waveplate and a liquid crystal variable retarder(LCVR).Experimental results demonstrate that our method can achieve illumination patterns with modulation depth higher than 0.94 at three orientations with only one LCVR voltage,which enables isotropic resolution improvement.展开更多
Object detection in occluded environments remains a core challenge in computer vision(CV),especially in domains such as autonomous driving and robotics.While Convolutional Neural Network(CNN)-based twodimensional(2D)a...Object detection in occluded environments remains a core challenge in computer vision(CV),especially in domains such as autonomous driving and robotics.While Convolutional Neural Network(CNN)-based twodimensional(2D)and three-dimensional(3D)object detection methods havemade significant progress,they often fall short under severe occlusion due to depth ambiguities in 2D imagery and the high cost and deployment limitations of 3D sensors such as Light Detection and Ranging(LiDAR).This paper presents a comparative review of recent 2D and 3D detection models,focusing on their occlusion-handling capabilities and the impact of sensor modalities such as stereo vision,Time-of-Flight(ToF)cameras,and LiDAR.In this context,we introduce FuDensityNet,our multimodal occlusion-aware detection framework that combines Red-Green-Blue(RGB)images and LiDAR data to enhance detection performance.As a forward-looking direction,we propose a monocular depth-estimation extension to FuDensityNet,aimed at replacing expensive 3D sensors with a more scalable CNN-based pipeline.Although this enhancement is not experimentally evaluated in this manuscript,we describe its conceptual design and potential for future implementation.展开更多
Workpiece rotational grinding is widely used in the ultra-precision machining of hard and brittle semiconductor materials,including single-crystal silicon,silicon carbide,and gallium arsenide.Surface roughness and sub...Workpiece rotational grinding is widely used in the ultra-precision machining of hard and brittle semiconductor materials,including single-crystal silicon,silicon carbide,and gallium arsenide.Surface roughness and subsurface damage depth(SDD)are crucial indicators for evaluating the surface quality of these materials after grinding.Existing prediction models lack general applicability and do not accurately account for the complex material behavior under grinding conditions.This paper introduces novel models for predicting both surface roughness and SDD in hard and brittle semiconductor materials.The surface roughness model uniquely incorporates the material’s elastic recovery properties,revealing the significant impact of these properties on prediction accuracy.The SDD model is distinguished by its analysis of the interactions between abrasive grits and the workpiece,as well as the mechanisms governing stress-induced damage evolution.The surface roughness model and SDD model both establish a stable relationship with the grit depth of cut(GDC).Additionally,we have developed an analytical relationship between the GDC and grinding process parameters.This,in turn,enables the establishment of an analytical framework for predicting surface roughness and SDD based on grinding process parameters,which cannot be achieved by previous models.The models were validated through systematic experiments on three different semiconductor materials,demonstrating excellent agreement with experimental data,with prediction errors of 6.3%for surface roughness and6.9%for SDD.Additionally,this study identifies variations in elastic recovery and material plasticity as critical factors influencing surface roughness and SDD across different materials.These findings significantly advance the accuracy of predictive models and broaden their applicability for grinding hard and brittle semiconductor materials.展开更多
文摘The initial noise present in the depth images obtained with RGB-D sensors is a combination of hardware limitations in addition to the environmental factors,due to the limited capabilities of sensors,which also produce poor computer vision results.The common image denoising techniques tend to remove significant image details and also remove noise,provided they are based on space and frequency filtering.The updated framework presented in this paper is a novel denoising model that makes use of Boruta-driven feature selection using a Long Short-Term Memory Autoencoder(LSTMAE).The Boruta algorithm identifies the most useful depth features that are used to maximize the spatial structure integrity and reduce redundancy.An LSTMAE is then used to process these selected features and model depth pixel sequences to generate robust,noise-resistant representations.The system uses the encoder to encode the input data into a latent space that has been compressed before it is decoded to retrieve the clean image.Experiments on a benchmark data set show that the suggested technique attains a PSNR of 45 dB and an SSIM of 0.90,which is 10 dB higher than the performance of conventional convolutional autoencoders and 15 times higher than that of the wavelet-based models.Moreover,the feature selection step will decrease the input dimensionality by 40%,resulting in a 37.5%reduction in training time and a real-time inference rate of 200 FPS.Boruta-LSTMAE framework,therefore,offers a highly efficient and scalable system for depth image denoising,with a high potential to be applied to close-range 3D systems,such as robotic manipulation and gesture-based interfaces.
文摘This study aims to develop an accurate and robust machine learning model to predict the carbonation depth of fly ash concrete,overcoming the limitations of traditional predictive methods.Five ensemble-based models,such as adaptive boosting(AdaBoost),categorical boosting(CatBoost),gradient boosting regressor(GBR),hist gradient boosting regressor(HistGBR),and extreme gradient boosting(XGBoost),were developed and optimized using 729 high-quality dataset points incorporating seven input parameters,including cement,CO_(2),exposure time,water-binder ratio,fly ash,curing time,and compressive strength.Several performance evaluation metrics were used to compare the models.The GBR model emerged as the best-performing model,based on high coefficient of determination(R^(2))values and balanced error metrics across both validation and testing datasets.While all models performed exceptionally well on the training data,GBR demonstrated superior generalization capability,with R^(2) values of 0.9438 on the validation set and 0.9310 on the testing set.Furthermore,its low mean squared error(MSE),root mean square error(RMSE),mean absolute error(MAE),and median absolute error(MdAE)confirmed its robustness and accuracy.Moreover,shapley additive explanations(SHAP)analysis enhanced the interpretability of predictions,highlighting the curing time and exposure time as the most critical drivers of carbonation depth.
文摘Objective:To explore the relationship between anesthetic depth and surgical stress response in minimally invasive cardiothoracic surgery.Methods:A total of 89 patients who underwent thoracoscopic minimally invasive cardiothoracic surgery in our hospital from June 2024 to December 2024 were selected as the research objects.They were divided into the light anesthesia group(n=45)and the deep anesthesia group(n=44).The vital signs at different intraoperative nodes and perioperative stress status of the two groups were compared.Results:Before lesion resection and after surgery,the mean arterial pressure and heart rate of the deep anesthesia group were lower than those of the light anesthesia group,with statistically significant differences.Conclusion:In thoracoscopic minimally invasive cardiothoracic surgery,deep anesthesia can effectively control the patient’s surgical stress response,but the postoperative awakening time is longer;patients under light anesthesia have a shorter awakening time,but the intraoperative stress response is obvious.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.12274348 and 12004335)the National Key Research and Development Program of China(Grant No.2024YFC2813800)。
文摘Presented in this study is a novel method for estimating the depth of single underwater source in shallow water,utilizing vector sensors.The approach leverages the depth distribution of the broadband Stokes parameters to estimate source depth accurately.Unlike traditional matched field processing(MFP)and matched mode processing(MMP),the proposed approach can estimate source depth directly from the data received by sensors without requiring complete environmental information.Firstly,the broadband Stokes parameters(BSP)are established using the normal mode theory.Then the nonstationary phase approximation is used to simplify the theoretical derivation,which is necessary when dealing with broadband integrals.Additionally,range terms of the BSP are eliminated by normalization.By analyzing the depth distribution of the normalized broadband Stokes parameters(NBSP),it is found that the NBSP exhibit extreme values at the source depth,which can be used for source depth estimation.So the proposed depth estimation method is based on searching the peaks of the NBSP.Simulations show that this method is effective in relatively simple shallow water environments.Finally,the effect of source range,frequency bandwidth,sound speed profile(SSP),water depth,and signal-to-noise ratio(SNR)are studied.The findings indicate that the proposed method can accurately estimate the source depth when the SNR is greater than-5 d B and does not need to consider model mismatch issues.Additionally,variations in environmental parameters have minimal impact on estimation accuracy.Compared to MFP,the proposed method requires a higher SNR,but demonstrates superior robustness against fluctuations in environmental parameters.
基金partially supported by the Natural Science Foundation of Shandong Province,China(No.ZR2023ME009)the National Natural Science Foundation of China(No.51909252)。
文摘Accurately estimating depth from underwater monocular images is essential for the target tracking task of unmanned underwater vehicles.This work proposes a method based on the Lpg-Lap Unet architecture.First,the Unet architecture integrates Laplacian pyramid depth residuals and Sobel operators to improve the boundary details in depth images,which may suffer from the feature loss caused by upsampling and the blurriness of underwater images.Multiscale local planar guidance layers then fully exploit the intermediate depth features,and a comprehensive loss function ensures robustness and accuracy.Experimental results on benchmarks demonstrate the effectiveness of Lpg-Lap Unet and its superior performance over state-of-the-art models.An underwater target tracking system is then designed to further validate its real-time capabilities in the AirSim simulation platform.
基金Supported by the National Natural Science Foundation of China(Nos.T2261149752,41976163,42476172)。
文摘Bathymetric measurement of shallow water is of fundamental importance to coastal environment research and resource management.However,there are still great challenges in estimating water depth using satellite observations in turbid coastal waters.In this paper,we developed a physicsenhanced deep neural network to estimate bathymetry of highly turbid waters of the Changjiang(Yangtze)River estuary from dual-polarized synthetic aperture radar(SAR)images.Sentinel-1A/B SAR images with a spatial resolution of 20 m×22 m were collected and matched with water depth data from nautical charts during 2017-2023.For the input parameters of the model,in addition to the normalized radar backscatter cross section(NRCS)at single polarization and incidence angle,the impacts of both polarimetric characteristics and physical environmental factors on model performance were discussed in detail.Results of feature importance analysis and sensitivity experiments indicate that the polarization ratio and NRCS after removing the influence of background sea surface wind field make significant contributions to the bathymetry retrieval model.The root mean square error(RMSE)of SAR derived water depth decreases from 1.44 to 0.78 m within 0-30-m depth,and the mean relative error(MRE)is reduced from 15.6%to 8.6%.Compared with other machine learning models such as ResNet,XGBoost,and Random Forest,the MRE is reduced by 3.9%,5.7%,and 7.4%,respectively.The spatial distribution of SAR derived water depth also exhibits a high degree of consistency with observations,demonstrating the great potential of the model in estimating the depth of turbid shallow waters.
文摘Depth maps play a crucial role in various practical applications such as computer vision,augmented reality,and autonomous driving.How to obtain clear and accurate depth information in video depth estimation is a significant challenge faced in the field of computer vision.However,existing monocular video depth estimation models tend to produce blurred or inaccurate depth information in regions with object edges and low texture.To address this issue,we propose a monocular depth estimation model architecture guided by semantic segmentation masks,which introduces semantic information into the model to correct the ambiguous depth regions.We have evaluated the proposed method,and experimental results show that our method improves the accuracy of edge depth,demonstrating the effectiveness of our approach.
基金supported in part by the National Natural Science Foundation of China under Grants 62071345。
文摘Self-supervised monocular depth estimation has emerged as a major research focus in recent years,primarily due to the elimination of ground-truth depth dependence.However,the prevailing architectures in this domain suffer from inherent limitations:existing pose network branches infer camera ego-motion exclusively under static-scene and Lambertian-surface assumptions.These assumptions are often violated in real-world scenarios due to dynamic objects,non-Lambertian reflectance,and unstructured background elements,leading to pervasive artifacts such as depth discontinuities(“holes”),structural collapse,and ambiguous reconstruction.To address these challenges,we propose a novel framework that integrates scene dynamic pose estimation into the conventional self-supervised depth network,enhancing its ability to model complex scene dynamics.Our contributions are threefold:(1)a pixel-wise dynamic pose estimation module that jointly resolves the pose transformations of moving objects and localized scene perturbations;(2)a physically-informed loss function that couples dynamic pose and depth predictions,designed to mitigate depth errors arising from high-speed distant objects and geometrically inconsistent motion profiles;(3)an efficient SE(3)transformation parameterization that streamlines network complexity and temporal pre-processing.Extensive experiments on the KITTI and NYU-V2 benchmarks show that our framework achieves state-of-the-art performance in both quantitative metrics and qualitative visual fidelity,significantly improving the robustness and generalization of monocular depth estimation under dynamic conditions.
基金supported by the National Natural Science Foundation of China [grant numbers 42088101 and 42375048]。
文摘Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical models.Machine learning can effectively solve this issue and has been proven useful in the prediction of groundwater depth in many areas.In this study,two new models are applied to the prediction of groundwater depth in the Ningxia area,China.The two models combine the improved dung beetle optimizer(DBO)algorithm with two deep learning models:The Multi-head Attention-Convolution Neural Network-Long Short Term Memory networks(MH-CNN-LSTM)and the Multi-head Attention-Convolution Neural Network-Gated Recurrent Unit(MH-CNN-GRU).The models with DBO show better prediction performance,with larger R(correlation coefficient),RPD(residual prediction deviation),and lower RMSE(root-mean-square error).Com-pared with the models with the original DBO,the R and RPD of models with the improved DBO increase by over 1.5%,and the RMSE decreases by over 1.8%,indicating better prediction results.In addition,compared with the multiple linear regression model,a traditional statistical model,deep learning models have better prediction performance.
基金Project supported by the National Natural Science Foundation of China(52372134,12274023)the Fundamental Re search Funds for the Central Universities(FRF-EYIT-23-04)。
文摘Rare earth-doped inorganic compounds contribute mostly to the family of persistent luminescent materials due to the versatile energy levels of rare earth ions.One of the key research aims is to match the trap level stemming from the doped rare earth ion or intrinsic defects to the electronic structure of the host,and therefore thermoluminescence measurement becomes a radical technology in studying trap depth,which is one of the significant parameters that determine the properties of persistent luminescence and photostimulated luminescence.However,the results of trap depth obtained by different thermoluminescence methods are quite different so that they are not comparable.Herein,we analyzed different thermoluminescence methods,selected and improved the traditional peak position method of T_(m)/500 to be E=(-0.94Inβ+30.09)kT_(m).Only the experimental heating rate(β)is needed additionally,but the accuracy is improved greatly in most cases.This convenient and accurate method will accelerate the discovery of novel rare earth-doped materials.
基金financially supported by the POSCO-POSTECH-RIST Convergence Research Center program funded by POSCOthe National Research Foundation (NRF) grants (RS-2024-00462912, RS-2024-00416272, RS-2024-00337012, RS-2024-00408446) funded by the Ministry of Science and ICT (MSIT) of the Korean government+2 种基金the Korea Evaluation Institute of Industrial Technology (KEIT) grant (No. 1415185027/20019169, Alchemist project) funded by the Ministry of Trade, Industry and Energy (MOTIE) of the Korean governmentthe Soseon Science fellowship funded by Community Chest of Koreathe NRF PhD fellowship (RS-2023-00275565) funded by the Ministry of Education (MOE) of the Korean government。
文摘Spatial computing and augmented reality are advancing rapidly,with the goal of seamlessly blending virtual and physical worlds.However,traditional depth-sensing systems are bulky and energy-intensive,limiting their use in wearable devices.To overcome this,recent research by X.Liu et al.presents a compact binocular metalens-based depth perception system that integrates efficient edge detection through an advanced neural network.This system enables accurate,realtime depth mapping even in complex environments,enhancing potential applications in augmented reality,robotics,and autonomous systems.
基金supported by National Natural Science Foundation of China(No.41504098 and 41504054)Natural Program on Key Basic Research Project(No.2015CB453002)
文摘The tilt-depth method can be used to make fast estimation of the top depth of magnetic bodies. However, it is unable to estimate bottom depths and its every inversion point only has a single solution. In order to resolve such weaknesses, this paper presents an improved tilt-depth method based on the magnetic anomaly expression of vertical contact with a finite depth extent, which can simultaneously estimate top and bottom depths of magnetic bodies. In addition, multiple characteristic points are selected on the tilt angle map for joint computation to improve reliability of inversion solutions. Two- and three- dimensional model tests show that this improved tilt-depth method is effective in inverting buried depths of top and bottom bodies, and has a higher inversion precision for top depths than the conventional method. The improved method is then used to process aeromagnetic data over the Changling Fault Depression in the Songliao Basin, and inversion results of top depths are found to be more accurate for actual top depths of volcanic rocks in two nearby drilled wells than those using the conventional tilt-depth method.
基金Project(2024ZD1003704)supported by the Deep Earth Probe and Mineral Resources Exploration-National Science and Technology Major Project,ChinaProjects(51834001,52130404)supported by the National Natural Science Foundation of China。
文摘During upward horizontal stratified backfill mining,stable backfill is essential for cap and sill pillar recovery.Currently,the primary method for calculating the required strength of backfill is the generalized three-dimensional(3 D)vertical stress model,which ignores the effect of mine depth,failing to obtain the vertical stress at different positions along stope length.Therefore,this paper develops and validates an improved 3 D model solution through numerical simulation in Rhino-FLAC^(3D),and examines the stress state and stability of backfill under different conditions.The results show that the improved model can accurately calculate the vertical stress at different mine depths and positions along stope length.The error rates between the results of the improved model and numerical simulation are below 4%,indicating high reliability and applicability.The maximum vertical stress(σ_(zz,max))in backfill is positively correlated with the degree of rock-backfill closure,which is enhanced by mine depth and elastic modulus of backfill,while weakened by stope width and inclination,backfill friction angle,and elastic modulus of rock mass.Theσ_(zz,max)reaches its peak when the stope length is 150 m,whileσ_(zz,max)is insensitive to changes in rock-backfill interface parameters.In all cases,the backfill stability can be improved by reducingσ_(zz,max).The results provide theoretical guidance for the backfill strength design and the safe and efficient recovery of ore pillars in deep mining.
基金Projects(52225403,52074112)supported by the National Natural Science Foundation of ChinaProject(2022CFD009)supported by the Hubei Natural Science Foundation Innovation and Development Joint Fund Key Project,China+2 种基金Project(SDGZK2423)supported by the State Key Laboratory of Intelligent Construction and Healthy Operation and Maintenance of Deep Underground Engineering,ChinaProject(HJZKYBKT2024111)supported by the Xiangyang Federation of Social Sciences“Hanjiang Think Tank”Project,ChinaProject supported by the Hubei Superior and Distinctive Discipline Group of“New Energy Vehicle and Smart Transportation”,China。
文摘Coal seam water injection in tunnels is an effective technical measure for preventing coal mine rock bursts.This study used the improved split Hopkinson pressure bar(SHPB)to apply three equal static stresses to water-saturated coal to simulate the initial stress environment of coal at different depths.Then,dynamic mechanical experiments were conducted on the saturated coal at different depths to investigate the effects of water saturation and depth on the coal samples’dynamic mechanical properties.Under uniaxial compression and without lateral compression,the strength of coal samples decreased to varying degrees in the saturated state;under different depth conditions,the dynamic strength of coal in the saturated state decreased compared with that in the natural state.However,compared with that at 0 m,the reduction in the strength of coal under the saturated condition at 200,400,600,and 800 m was significantly reduced.The findings of this study provide a basic theoretical foundation for the prevention and control of dynamic coal mine disasters.
基金funded by the National Natural Science Foundation of China(Grant No.31801421)the Chinese Academy of Agricultural Sciences Innovation Project(Grant No.CAAS-ASTIPIVFCAAS).
文摘Eye depth is an important agronomic trait affecting tubers'appearance,quality,and processing suitability.Hence,cultivating varieties with uniform shapes and shallow eye depth are important goals for potato breeding.In this study,based on the primary mapping of the tuber eyedepth locus using a small primary-segregating population,a large secondary-segregating population with 2100 individuals was used to map the eye-depth locus further.A major quantitative trait locus for eye-depth on chromosome 10 was identified(designated qEyd10.1)using BSAseq and traditional QTL mapping methods.The qEyd10.1 could explain 55.0%of the eye depth phenotypic variation and was further narrowed to a 309.10 kb interval using recombinant analysis.To predict candidate genes,tissue sectioning and RNA-seq of the specific tuber tissues were performed.Genes encoding members of the peroxidase superfamily with likely roles in indole acetic acid regulation were considered the most promising candidates.These results will facilitate marker-assisted selection for the shallow-eye trait in potato breeding and provide a solid basis for eye-depth gene cloning and the analysis of tuber eye-depth regulatory mechanisms.
文摘AIM:To assess visual outcomes and satisfaction of a non-diffractive extended depth of focus(EDOF)intraocular lens(IOL)in individuals with ocular hypertension(OHT)and well-controlled mild glaucoma undergoing cataract surgery.METHODS:An investigator-initiated,single-center,prospective,interventional,noncomparative study conducted in Montreal,Canada.The study enrolled 31 patients(55 eyes)with OHT or mild glaucoma who received a non-diffractive EDOF IOL(Acrysof IQ Vivity).Participants underwent sequential cataract surgery with the Vivity IOL.Follow-up evaluations occurred at 1d,1,and 3mo postoperatively,assessing uncorrected distance,intermediate,and near visual acuity.Questionnaires(QUVID:Questionnaire for visual disturbances and IOLSAT:Intraocular lens satisfaction)were administered pre and post-operatively to measure visual disturbances and spectacle independence in various lighting.Safety parameters included intraocular pressure(IOP),glaucoma medications,spherical equivalence,mean deviation and pattern standard deviation or square root of lost variance on Octopus visual field.RESULTS:At 1 and 3mo postoperatively,significant improvements were observed in uncorrected distance and intermediate visual acuity.Spectacle independence was enhanced for distance and intermediate vision,especially in bright light settings.Spectacle-free intermediate vision was improved even in dim lighting.Visual disturbances,particularly glare symptoms,were reduced,and there was a notable decrease in IOP and glaucoma medication burden at 3mo.There was more hazy vision postoperatively with no impact on visual acuity and visual satisfaction.CONCLUSION:The non-diffractive EDOF lens improves distance and intermediate spectacle-free visual function in patients with OHT and well-controlled glaucoma.The findings highlight significant improvements in visual acuity,reduced glare,enhanced spectacle independence,and improved visual performance in different lighting conditions.
基金supported by the National Natural Science Foundation of China[Grant Nos.62205367 and 62141506]the Suzhou Basic Research Pilot Project[Grant Nos.SSD2023006 and SJC2021013]the National Key Research and Development Program of China[Grant No.2023YFF1205700].
文摘Maintaining the s-polarization state of laser beams is important to achieve high modulation depth in a laser-interference-based super-resolution structured illumination microscope(SR-SIM).However,the imperfect optical components can depolarize the laser beams hence degenerating the modulation depth.Here,we first presented a direct measurement method designed to estimate the modulation depth more precisely by shifting illumination patterns with equal phase steps.This measurement method greatly reduces the dependence of modulation depths on the samples,and then developed a polarization optimization method to achieve high modulation depth at all orientations by actively and quantitatively compensating for the additional phase difference using a combination of waveplate and a liquid crystal variable retarder(LCVR).Experimental results demonstrate that our method can achieve illumination patterns with modulation depth higher than 0.94 at three orientations with only one LCVR voltage,which enables isotropic resolution improvement.
文摘Object detection in occluded environments remains a core challenge in computer vision(CV),especially in domains such as autonomous driving and robotics.While Convolutional Neural Network(CNN)-based twodimensional(2D)and three-dimensional(3D)object detection methods havemade significant progress,they often fall short under severe occlusion due to depth ambiguities in 2D imagery and the high cost and deployment limitations of 3D sensors such as Light Detection and Ranging(LiDAR).This paper presents a comparative review of recent 2D and 3D detection models,focusing on their occlusion-handling capabilities and the impact of sensor modalities such as stereo vision,Time-of-Flight(ToF)cameras,and LiDAR.In this context,we introduce FuDensityNet,our multimodal occlusion-aware detection framework that combines Red-Green-Blue(RGB)images and LiDAR data to enhance detection performance.As a forward-looking direction,we propose a monocular depth-estimation extension to FuDensityNet,aimed at replacing expensive 3D sensors with a more scalable CNN-based pipeline.Although this enhancement is not experimentally evaluated in this manuscript,we describe its conceptual design and potential for future implementation.
基金supported by the National Key Research and Development Program of China(2022YFB3605902)the National Natural Science Foundation of China(52375411,52293402)。
文摘Workpiece rotational grinding is widely used in the ultra-precision machining of hard and brittle semiconductor materials,including single-crystal silicon,silicon carbide,and gallium arsenide.Surface roughness and subsurface damage depth(SDD)are crucial indicators for evaluating the surface quality of these materials after grinding.Existing prediction models lack general applicability and do not accurately account for the complex material behavior under grinding conditions.This paper introduces novel models for predicting both surface roughness and SDD in hard and brittle semiconductor materials.The surface roughness model uniquely incorporates the material’s elastic recovery properties,revealing the significant impact of these properties on prediction accuracy.The SDD model is distinguished by its analysis of the interactions between abrasive grits and the workpiece,as well as the mechanisms governing stress-induced damage evolution.The surface roughness model and SDD model both establish a stable relationship with the grit depth of cut(GDC).Additionally,we have developed an analytical relationship between the GDC and grinding process parameters.This,in turn,enables the establishment of an analytical framework for predicting surface roughness and SDD based on grinding process parameters,which cannot be achieved by previous models.The models were validated through systematic experiments on three different semiconductor materials,demonstrating excellent agreement with experimental data,with prediction errors of 6.3%for surface roughness and6.9%for SDD.Additionally,this study identifies variations in elastic recovery and material plasticity as critical factors influencing surface roughness and SDD across different materials.These findings significantly advance the accuracy of predictive models and broaden their applicability for grinding hard and brittle semiconductor materials.
